StylOS: Multi-View 3D Stylization with Single-Forward Gaussian Splatting

ICLR 2026 Conference Submission15555 Authors

Keywords: 3D Style Transfer, 3D Gaussian Splatting, Single-forward Stylization, 3D Reconstruction

TL;DR: StylOS is a single-pass framework that performs geometry-aware, view-consistent 3D style transfer from unposed content images using a reference style image, without per-scene optimization or precomputed poses.

Abstract:

We present Stylos, a single-forward 3D Gaussian framework for 3D style
transfer that operates on unposed content, from a single image to a multi-
view collection, conditioned on a separate reference style image. Stylos
synthesizes a stylized 3D Gaussian scene without per-scene optimization or
precomputed poses, achieving geometry-aware, view-consistent stylization
that generalizes to unseen categories, scenes, and styles. At its core, Stylos
adopts a Transformer backbone with two pathways: geometry predictions
retain self-attention to preserve geometric fidelity, while style is injected
via global cross-attention to enforce visual consistency across views. With
the addition of a voxel-based 3D style loss that aligns aggregated scene
features to style statistics, Stylos enforces view-consistent stylization while
preserving geometry. Experiments across multiple datasets demonstrate
that Stylos delivers high-quality zero-shot stylization, highlighting the ef-
fectiveness of global style–content coupling, the proposed 3D style loss, and
the scalability of our framework from single view to large-scale multi-view
settings. Our codes will be fully open-sourced soon.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 15555